Development and validation of an interpretable machine learning model for osteoporosis prediction using routine blood tests: a retrospective cohort study | BMC Medical Informatics and Decision Making

Machine Learning


  • Cotts KG, Cifu AS. Treatment of osteoporosis. JAMA. 2018;319(10):1040–1.

    Google Scholar 

  • Tuck S, Little EA, Aspray TJ. Implications of guidelines for osteoporosis and its treatment. Age Ageing. 2018;47(3):334–9.

    Google Scholar 

  • Cauley JA. Screening for osteoporosis. JAMA. 2018;319(24):2483–5.

    Google Scholar 

  • Ong W, Liu RW, Makmur A, Low XZ, Sng WJ, Tan JH, Kumar N, Hallinan J. Artificial intelligence applications for osteoporosis classification using computed tomography. Bioengeering 2023, 10(12).

  • Tan J, Zhang Z, He Y, Xu X, Yang Y, Xu Q, Yuan Y, Wu X, Niu J, Tang S, Wu X, Hu Y. Development and validation of a risk prediction model for osteoporosis in elderly patients with type 2 diabetes mellitus: a retrospective and multicenter study. BMC Geriatr. 2023;23(1):698.

    Google Scholar 

  • Chanprasertpinyo W, Punsawad C, Khwanchuea R, Sukkriang N, Yincharoen P, Rerkswattavorn C. Comparison between calcaneus quantitative ultrasound and the gold standard DXA in the ability to detect osteoporosis in chronic obstructive pulmonary disease patients. J Orthop Surg Res. 2023;18(1):778.

    Google Scholar 

  • Lin S, Luo Y, Xie Y, Liao Y, Niu S, Zheng Y, Que Q, Ye S, Liu F, Feng L, Yan W, Duan C, Yang D. The development and validation of a prediction model for imminent vertebral osteoporotic fracture in postmenopausal women. Eur Spine J; 2024.

  • Si L, Eisman JA, Winzenberg T, Sanders KM, Center JR, Nguyen TV, Tran T, Palmer AJ. Development and validation of the risk engine for an Australian health economics model of osteoporosis. Osteoporos Int. 2021;32(10):2073–81.

    Google Scholar 

  • Lee C, Joo G, Shin S, Im H, Moon KW. Prediction of osteoporosis in patients with rheumatoid arthritis using machine learning. Sci Rep. 2023;13(1):21800.

    Google Scholar 

  • Gao Y, McGagh D, Ding L, Hong S, Ouyang Z, Wei J, Zeng C, Lei G, Xie J. Hospital-Treated infections and 15-year incidence of musculoskeletal disorders: A large Population-Based cohort study. Clin Epidemiol. 2025;17:251–64.

    Google Scholar 

  • An F, Jia X, Shi Y, Xiao X, Yang F, Su J, Peng X, Geng G, Yan C. The ultimate microbial composition for correcting Th17/Treg cell imbalance and lipid metabolism disorders in osteoporosis. Int Immunopharmacol. 2025;144:113613.

    Google Scholar 

  • Yang M, Zhu L, Osteoimmunology. The crosstalk between T Cells, B Cells, and osteoclasts in rheumatoid arthritis. Int J Mol Sci. 2024, 25(5).

  • Lin N, Li D, Lin S, Ke Y, Lu J, Wu Y, Huang T, Hong H. The Monocyte-to-High-Density lipoprotein cholesterol ratio as a novel predictor of the prevalence of senile osteoporosis. Clin Interv Aging. 2024;19:1773–88.

    Google Scholar 

  • Yousefiasl M, Soltanattar A, Ezzatollahi TA, Azami P, Alaei M, Alamdari AA, Esmailsorkh F, Habibzadeh A, Khanmohammadi S. Association of triglyceride-glucose index with bone mineral density and fracture: a systematic review. Diabetol Metab Syndr. 2025;17(1):77.

    Google Scholar 

  • Huang G, Zhu W, Wang Y, Wan Y, Chen K, Su Y, Su W, Li L, Liu P, Dong GX. Can some algorithms of machine learning identify osteoporosis patients after training and testing some clinical information about patients? BMC Med Inform Decis Mak. 2025;25(1):127.

    Google Scholar 

  • Wu Y, Zhao C, Li Y, Zhu S, Zhang C, Zhu Z, Xia W, Wang K. Nomogram for predicting cemented vertebral refracture after percutaneous kyphoplasty in postmenopausal women with osteoporotic vertebral compression fractures. Clin Neurol Neurosurg. 2025;250:108789.

    Google Scholar 

  • Wang L, Xu D, Chen M, Huang X. Association of neutrophil to high-density lipoprotein cholesterol ratio with fragility fracture in osteoporotic patients: a case-control study. BMC Musculoskelet Disord. 2025;26(1):193.

    Google Scholar 

  • Ye H, Chen Z, Li K, Zhang Y, Li H, Tian N. Non-linear association of the platelet/high-density lipoprotein cholesterol ratio with bone mineral density a cross-sectional study. Lipids Health Dis. 2024;23(1):300.

    Google Scholar 

  • Fu Q, Zhang C, Yang Y, Teng R, Liu F, Liu P, Wang L, Wang J, Chen Y, Ding Y. Correlation study of multiple inflammatory indices and vertebral compression fracture: A cross-sectional study. J Clin Transl Endocr. 2024;37:100369.

    Google Scholar 

  • Mo D, Zhang P, Zhang M, Dai H, Guan J. Cholesterol, high-density lipoprotein, and glucose index versus triglyceride-glucose index in predicting cardiovascular disease risk: a cohort study. Cardiovasc Diabetol. 2025;24(1):116.

    Google Scholar 

  • Sanchez-Pinto LN, Venable LR, Fahrenbach J, Churpek MM. Comparison of variable selection methods for clinical predictive modeling. Int J Med Inf. 2018;116:10–7.

    Google Scholar 

  • Guan C, Gong A, Zhao Y, Yin C, Geng L, Liu L, Yang X, Lu J, Xiao B. Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study. Crit Care. 2024;28(1):349.

    Google Scholar 

  • Huang D, Gong L, Wei C, Wang X, Liang Z. An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease. Resp Res. 2024;25(1):246.

    Google Scholar 

  • Bhandari M, Shahi TB, Siku B, Neupane A. Explanatory classification of CXR images into COVID-19, pneumonia and tuberculosis using deep learning and XAI. Comput Biol Med. 2022;150:106156.

    Google Scholar 

  • Patel AN, Murugan R, Srivastava G, Maddikunta PKR, Yenduri G, Gadekallu TR, Chengoden R. An explainable transfer learning framework for multi-classification of lung diseases in chest X-rays. Alex Eng J. 2024;98:328–43.

    Google Scholar 

  • Yu F, Xia W. The epidemiology of osteoporosis, associated fragility fractures, and management gap in China. Arch Osteoporos. 2019;14(1):32.

    Google Scholar 

  • Sadat-Ali M, Alzahrani BA, Alqahtani TS, Alotaibi MA, Alhalafi AM, Alsousi AA, Alasiri AM. Accuracy of artificial intelligence in prediction of osteoporotic fractures in comparison with dual-energy X-ray absorptiometry and the fracture risk assessment tool: A systematic review. World J Orthop. 2025;16(4):103572.

    Google Scholar 

  • Shen J, Fang W, Zhu Y, Ye C, Zhu Y, Tao Y. Utilization of preventative health checkup services in China among middle-aged and older adult population: evidence from china’s 28 provinces. Front Public Health. 2025;13:1500018.

    Google Scholar 

  • Metrailler A, Hans D, Lamy O, Gonzalez RE, Shevroja E. Heel quantitative ultrasound (QUS) predicts incident fractures independently of trabecular bone score (TBS), bone mineral density (BMD), and FRAX: the osteolaus study. Osteoporos Int. 2023;34(8):1401–9.

    Google Scholar 

  • Schraders K, Zatta G, Kruger M, Coad J, Weber J, Brough L, Thomson J. Quantitative Ultrasound and Dual X-Ray Absorptiometry as Indicators of Bone Mineral Density in Young Women and Nutritional Factors Affecting It. Nutrients. 2019, 11(10).

  • Saxena Y, Routh S, Mukhopadhaya A, Immunoporosis. Role of innate immune cells in osteoporosis. Front Immunol. 2021;12:687037.

    Google Scholar 

  • Zhang Z, Liu J, Li Y, Wang Y, Zheng X, Wang F, Tong T, Miao D, Li W, Chen L, Wang L. 4-Hydroxyphenylacetic Acid, a microbial-derived metabolite of Polyphenols, inhibits osteoclastogenesis by inhibiting ROS production. Int Immunopharmacol. 2024;143(3):113571.

    Google Scholar 

  • Da W, Jiang W, Tao L. ROS/MMP-9 mediated CS degradation in BMSC inhibits citric acid metabolism participating in the dual regulation of bone remodelling. Cell Death Discov. 2024;10(1):77.

    Google Scholar 

  • Zhang M, Sun J, Zhao H, Liu Y, Tang Z, Wen Y, Ma Q, Zhang L, Zhang Y. Alginate oligosaccharides relieve estrogen-deprived osteosarcopenia by affecting intestinal Th17 differentiation and systemic inflammation through the manipulation of bile acid metabolism. Int J Biol Macromol. 2025;295:139581.

    Google Scholar 

  • Gu P, Pu B, Xin Q, Yue D, Luo L, Tao J, Li H, Chen M, Hu M, Hu X, Zheng X, Zeng Z. The metabolic score of insulin resistance is positively correlated with bone mineral density in postmenopausal patients with type 2 diabetes mellitus. Sci Rep. 2023;13(1):8796.

    Google Scholar 

  • Zhan J, Wei Q, Guo W, Liu Z, Chen S, Huang Q, Liang S, Cai D. Evaluating the triglyceride glucose index as a predictive biomarker for osteoporosis in patients with type 2 diabetes. Front Endocrinol. 2025;16:1534232.

    Google Scholar 

  • Chang CY, Peng CH, Chen FY, Huang LY, Kuo CH, Chu TW, Liang YJ. The risk factors determined by four machine learning methods for the change of difference of bone mineral density in post-menopausal women after three years follow-up. Sci Rep. 2024;14(1):23234.

    Google Scholar 

  • Lin Y, Jiang S, Yao Y, Li H, Jin H, Yang G, Ji B, Li Y. Posttranslational modification in bone homeostasis and osteoporosis. Medcomm. 2025;6(4):e70159.

    Google Scholar 

  • Zhou Y, Yang Y, Zhu W, Kourkoumelis N, Wang Y, Chen Y, Hong L, Wang J, Zhu J, Zhu C, Zhang X. Microbial influences on Calcium-Phosphorus homeostasis and metabolic bone diseases: A bidirectional Mendelian randomisation study on the Gut-Bone axis. J Cell Mol Med. 2025;29(7):e70491.

    Google Scholar 

  • Zhang Y, Cui Y, Sun C, Guo J, Li M. ED-71 ameliorates OVX-induced osteoporosis by regulating calcium homeostasis and SIRT1-mediated mitochondrial function, alleviating osteoblast senescence and suppressing osteoclastogenesis. Cell Signal. 2025;131:111713.

    Google Scholar 

  • Zheng HW, Bui A, Ensrud KE, Wright NC, Manson JE, Watts NB, Johnson KC, Shadyab AH, Crandall CJ. Identifying younger postmenopausal women with osteoporosis using USPSTF-Recommended osteoporosis risk assessment tools. JAMA Netw Open. 2025;8(3):e250626.

    Google Scholar 

  • Binkley N, Coursin D, Krueger D, Iglar P, Heiner J, Illgen R, Squire M, Lappe J, Watson P, Hogan K. Surgery alters parameters of vitamin D status and other laboratory results. Osteoporos Int. 2017;28(3):1013–20.

    Google Scholar 

  • Kristjansdottir HL, Mellstrom D, Johansson P, Karlsson M, Vandenput L, Lorentzon M, Herlitz H, Ohlsson C, Lerner UH, Lewerin C. High platelet count is associated with low bone mineral density: the MrOS Sweden cohort. Osteoporos Int. 2021;32(5):865–71.

    Google Scholar 

  • Lin KM, Lu CL, Hung KC, Wu PC, Pan CF, Wu CJ, Syu RS, Chen JS, Hsiao PJ, Lu KC. The Paradoxical Role of Uric Acid in Osteoporosis. Nutrients. 2019, 11(9).

  • Li LP, Chen XY, Liu HB, Zhu Y, Xie MJ, Li YJ, Luo M, Albahde M, Zhang HY, Lou JY. Oxidative stress-induced circSOD2 inhibits osteogenesis through sponging miR-29b in metabolic-associated fatty liver disease. World J Gastroentero. 2025;31(9):98027.

    Google Scholar 

  • Nagao N, Wakabayashi H, Miyamura G, Kato S, Naito Y, Sudo A. CTLA-4Ig Improves Hyperalgesia in a Mouse Model of Osteoporosis. Int J Mol Sci. 2020, 21(24).

  • Wang J, Li S, Pu H, He J. The association between the non-high-density lipoprotein cholesterol to high-density lipoprotein cholesterol ratio and the risk of osteoporosis among U.S. Adults: analysis of NHANES data. Lipids Health Dis. 2024;23(1):161.

    Google Scholar 

  • Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics. 2020;21(1):6.

    Google Scholar 

  • Couronne R, Probst P, Boulesteix AL. Random forest versus logistic regression: a large-scale benchmark experiment. BMC Bioinformatics. 2018;19(1):270.

    Google Scholar 

  • Moayyeri A, Adams JE, Adler RA, Krieg MA, Hans D, Compston J, Lewiecki EM. Quantitative ultrasound of the heel and fracture risk assessment: an updated meta-analysis. Osteoporos Int. 2012;23(1):143–53.

    Google Scholar 



  • Source link